INDEX

Explanations

terms related to forensic evidence and identification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

HomeAsUpEnabled

-0.59

hyrchwyd

-0.52

ÍAS

-0.49

 frank

-0.49

vinger

-0.48

 compréhen

-0.48

 ModelExpression

-0.47

apu

-0.47

 Parsons

-0.46

HandleFunc

-0.46

POSITIVE LOGITS

 Paglinawan

0.72

 TextAppearance

0.63

 EconPapers

0.61

 Italijani

0.60

 Sélectionnez

0.58

ANTLR

0.56

RegistryLite

0.55

 identidade

0.55

 matches

0.54

 betweenstory

0.53

Activations Density 0.502%

terms related to forensic evidence and identification

No Comments

No Known Activations